Sarvesh Chandra

Software Engineer

Bengaluru, Karnataka, India5 yrs experience

AI EnabledAI ML Practitioner

Key Highlights

Expert in compiler optimization and AI-driven automation.
Proficient in modern C++ and emerging language features.
Recognized for academic excellence and impactful projects.

Stackforce AI infers this person is a specialist in AI/ML and Compiler Engineering.

Contact

sarveshchandra0478@gmail.com LinkedIn

Skills

Core Skills

C++CompilersDeep LearningNatural Language Processing (nlp)System ArchitectureMachine LearningData ScienceSoftware Architecture

Other Skills

Amazon Web Services (AWS)Audio ProcessingBashC (Programming Language)CPPChatbot DevelopmentClangComputer NetworkingComputer VisionContainerizationContinuous Integration and Continuous Delivery (CI/CD)Conversational AIConvolutional Neural Networks (CNN)CryptographyData Analysis

About

I’m part of the Compiler Engineering team at AMD, focusing on optimizing HPC workloads to harness the full capabilities of AMD’s latest CPU architectures. My work involves enhancing code generation, tuning performance-critical compiler passes, and contributing upstream to open-source ecosystems like GCC and LLVM. I primarily work in modern C++ (up to C++26), extending compiler support for emerging language features. In parallel, I build AI-driven automation agents to streamline repetitive aspects of the software development lifecycle, integrating intelligent tooling into the compiler engineering workflow. Previously, I worked at Samsung’s Advanced Institute of Technology (SAIT) in the AI Computing division, developing compilers, accelerators, and processors for AI/ML workloads, along with LLM-aided inference engines for automation. My expertise spans C++ and Python, compiler optimization, algorithms, GenAI, RAG, and systems-level programming. I hold a B.Tech in Electrical Engineering from IIT Kanpur with minors in Computer Systems and Algorithms, and have earned recognitions including the Academic Excellence Award and the KVPY scholarship.

Experience

5 yrs

Total Experience

1 yr 6 mos

Average Tenure

8 mos

Current Experience

Amd

SWE II - Compilers (GCC/AOCC)

Oct 2025 – Present · 8 mos · Bengaluru, Karnataka, India · On-site

C++CompilersLLVMGCCClangGenAI+3

Samsung semiconductor

2 roles

SWE I - SAIT (AI Computing)

Jun 2023 – Oct 2025 · 2 yrs 4 mos · Bengaluru, Karnataka, India · On-site

Built compiler for Processing-In-Memory (PIM) to accelerate AI workloads
Built LLM aided pair programming CLI/web application - RAG, code generation, fine tuning
Designed parallelization passes for algorithmic translation of PIM compiler IR to OpenCL kernels for execution of GEMV on GPU-PIM
Modelled in SystemC the L1 DCache in a multi level coherent cache system in a multi-core supercomputer architecture.
Modelled and tested in SystemC a robust, multi precision matrix multiplication unit for an AI accelerator along with the synchronous exchanges between its stager and router

C++Deep LearningLow Level ProgrammingRetrieval-Augmented Generation (RAG)Modeling and SimulationLarge Language Models (LLM)+8

SWE Intern

May 2022 – Jul 2022 · 2 mos · India

Assisted in the performance analysis of Processing-In-Memory (PIM) architecture by configuring an interface which delivers reads and writes from a cycle accurate CPU simulator to a memory simulator (DRAM or PIM).

C++System ArchitectureBashSystem PerformanceCPPOperating Systems+1

Pariksha

Machine Learning and Software Development Intern

May 2021 – Aug 2021 · 3 mos · India

Categorized misrepresented data and gave the data the intended representation using ML (LSTM and GRU). Used AWS batch jobs to accelerate the work. Could show a reduction in time for creating exams from ~30 hours to a few minutes

Data AnalysisMachine LearningData MiningBashPython (Programming Language)Recurrent Neural Networks (RNN)+2